# Underwater Image Enhancement with Physical-based Denoising Diffusion Implicit Models

arXiv: https://arxiv.org/abs/2409.18476 · HTML: https://mlsanity.com/paper/2409.18476/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 22 of its 62 references that are in the map.
- First posted on arXiv 27 Sep 2024.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 22 of 22)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Denoising Diffusion Restoration Models](https://mlsanity.com/paper/2201.11793/) (2022)
- [UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models](https://mlsanity.com/paper/2302.04867/) (2023)
- [YOLACT: Real-time Instance Segmentation](https://mlsanity.com/paper/1904.02689/) (2019)
- [SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models](https://mlsanity.com/paper/2104.14951/) (2021)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [A Variational Perspective on Solving Inverse Problems with Diffusion Models](https://mlsanity.com/paper/2305.04391/) (2023)
- [Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models](https://mlsanity.com/paper/2207.14626/) (2022)
- [Fast Underwater Image Enhancement for Improved Visual Perception](https://mlsanity.com/paper/1903.09766/) (2019)
- [WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images](https://mlsanity.com/paper/1702.07392/) (2017)
- [U-shape Transformer for Underwater Image Enhancement](https://mlsanity.com/paper/2111.11843/) (2021)
- [Enhancing Underwater Imagery using Generative Adversarial Networks](https://mlsanity.com/paper/1801.04011/) (2018)
- [Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset](https://mlsanity.com/paper/1811.01343/) (2018)
- [Shallow-UWnet : Compressed Model for Underwater Image Enhancement](https://mlsanity.com/paper/2101.02073/) (2021)
- [Underwater Image Enhancement based on Deep Learning and Image Formation Model](https://mlsanity.com/paper/2101.00991/) (2021)
- [MLFcGAN: Multi-level Feature Fusion based Conditional GAN for Underwater Image Color Correction](https://mlsanity.com/paper/2002.05333/) (2020)
- [Tracking Live Fish from Low-Contrast and Low-Frame-Rate Stereo Videos](https://mlsanity.com/paper/1504.03811/) (2015)

## Built on by (most cited first, 1 of 1)

- [LOBSTgER-enhance: an underwater image enhancement pipeline](https://mlsanity.com/paper/2602.05163/) (2026)

## Abstract (arXiv)

Underwater vision is crucial for autonomous underwater vehicles (AUVs), and enhancing degraded underwater images in real-time on a resource-constrained AUV is a key challenge due to factors like light absorption and scattering, or the sufficient model computational complexity to resolve such factors. Traditional image enhancement techniques lack adaptability to varying underwater conditions, while learning-based methods, particularly those using convolutional neural networks (CNNs) and generative adversarial networks (GANs), offer more robust solutions but face limitations such as inadequate enhancement, unstable training, or mode collapse. Denoising diffusion probabilistic models (DDPMs) have emerged as a state-of-the-art approach in image-to-image tasks but require intensive computational complexity to achieve the desired underwater image enhancement (UIE) using the recent UW-DDPM solution. To address these challenges, this paper introduces UW-DiffPhys, a novel physical-based and diffusion-based UIE approach. UW-DiffPhys combines light-computation physical-based UIE network components with a denoising U-Net to replace the computationally intensive distribution transformation U-Net in the existing UW-DDPM framework, reducing complexity while maintaining performance. Additionally, the Denoising Diffusion Implicit Model (DDIM) is employed to accelerate the inference process through non-Markovian sampling. Experimental results demonstrate that UW-DiffPhys achieved a substantial reduction in computational complexity and inference time compared to UW-DDPM, with competitive performance in key metrics such as PSNR, SSIM, UCIQE, and an improvement in the overall underwater image quality UIQM metric. The implementation code can be found at the following repository: https://github.com/bachzz/UW-DiffPhys